gimchi 0.1.0

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2011 Junegunn Choi
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.ko.rdoc

@@ -0,0 +1,116 @@
+# encoding: UTF-8
+
+= gimchi
+
+== 개요
+
+Gimchi는 한글 스트링을 다롭니다.
+국립 국어원 어문 규정에 정의된 한글의 표준 발음법과
+로마자 표기법을 (일부) 구현한 것이 주요 기능입니다.
+
+또한 다음의 기능들을 제공합니다.
+- 주어진 캐릭터가 한글인지 판단
+- 한글을 초성, 중성, 종성으로 분리하고, 이를 다시 합치는 기능
+- 숫자 표기를 한글 표현으로 변환
+
+== 사용법
+
+=== Gimchi::Korean 인스턴스의 생성
+  ko = Gimchi::Korean.new
+
+=== 한글 캐릭터 여부 판단
+  ko.korean_char? 'ㄱ'           # true
+  ko.complete_korean_char? 'ㄱ'  # false
+
+  ko.korean_char? 'ㅏ'           # true
+  ko.complete_korean_char? 'ㅏ'  # false
+
+  ko.korean_char? '가'           # true
+  ko.complete_korean_char? '가'  # true
+
+=== Gimchi::Korean::Char
+  arr = ko.dissect '이것은 한글입니다.'
+    # [이, 것, 은, " ", 한, 글, 입, 니, 다, "."]
+
+  arr[4].class                   # Gimchi::Korean::Char
+
+  arr[4].chosung                 # "ㅎ"
+  arr[4].jungsung                # "ㅏ"
+  arr[4].jongsung                # "ㄴ"
+  arr[4].to_a                    # ["ㅎ", "ㅏ", "ㄴ"]
+  arr[4].to_s                    # "한"
+
+  arr[4].chosung = 'ㄷ'
+  arr[4].jongsung = 'ㄹ'
+  arr[4].to_s                    # "달"
+  arr[4].complete?               # true
+  arr[4].partial?                # false
+
+  arr[4].chosung = nil
+  arr[4].jongsung = nil
+  arr[4].complete?               # false
+  arr[4].partial?                # true
+
+=== 숫자 읽기
+  ko.read_number(1999)         # "천 구백 구십 구"
+  ko.read_number(- 100.123)    # "마이너스 백점일이삼"
+  ko.read_number("153,101,202,333.321")
+  ko.read_number("153,191,100,678.3214")
+    	# "천 오백 삼십 일억 구천 백 십만 육백 칠십 팔점삼이일사"
+
+  # 나이, 시간 ( -살, -시 )
+  ko.read_number("20살")       # "스무살"
+  ko.read_number("13 살")      # "열세 살"
+  ko.read_number("7시 30분")   # "일곱시 삼십분"
+
+=== 표준 발음 (부분 구현)
+  str = "됐어 됐어 이제 그런 가르침은 됐어 매일 아침 7 시 30 분까지 우릴 조그만 교실로 몰아넣고"
+  ko.pronounce str
+    # "돼써 돼써 이제 그런 가르치믄 돼써 매일 아침 일곱 시 삼십 분까지 우릴 조그만 교실로 모라너코"
+
+  ko.pronounce str, :slur => true
+    # "돼써 돼써 이제 그런 가르치믄 돼써 매이 라치 밀곱 씨 삼십 뿐까지 우릴 조그만 교실로 모라너코"
+
+  ko.pronounce str, :pronounce_each_char => true
+    # "됃어 됃어 이제 그런 가르침은 됃어 매일 아침 일곱 시 삼십 분까지 우릴 조그만 교실로 몰아너고"
+
+  ko.pronounce str, :number => false
+    # "돼써 돼써 이제 그런 가르치믄 돼써 매일 아침 7 시 30 분까지 우릴 조그만 교실로 모라너코"
+
+=== 로마자 표기 (부분 구현)
+  str = "됐어 됐어 이제 그런 가르침은 됐어 매일 아침 7 시 30 분까지 우릴 조그만 교실로 몰아넣고"
+
+  ko.romanize str
+    # "Dwaesseo dwaesseo ije geureon gareuchimeun dwaesseo mae-il achim ilgop si samsip bunkkaji uril jogeuman gyosillo moraneoko"
+  ko.romanize str, :slur => true
+    # "Dwaesseo dwaesseo ije geureon gareuchimeun dwaesseo mae-i rachi milgop ssi samsip ppunkkaji uril jogeuman gyosillo moraneoko"
+  ko.romanize str, :as_pronounced => false
+    # "Dwaet-eo dwaet-eo ije geureon gareuchim-eun dwaet-eo mae-il achim ilgop si samsip bunkkaji uril jogeuman gyosillo mol-aneogo"
+  ko.romanize str, :number => false
+	# "Dwaesseo dwaesseo ije geureon gareuchimeun dwaesseo mae-il achim 7 si 30 bunkkaji uril jogeuman gyosillo moraneoko"
+
+== 구현의 한계
+
+표준 발음법과 로마어 표기법을 모두 구현하기 위해서는 형태소 분석과 충분한
+사전, 그리고 문맥의 의미 분석이 필요합니다. 이 모든 것이 준비된다고 할 지라도
+완벽한 결과를 얻는 것은 불가능합니다.
+이는 현재 gimchi가 목표로 하는 것이 아니며 gimchi는 간단한 구현으로 어느 수준
+이상의 결과를 얻는 것을 목표로 합니다. 현재 구현의 한계 내에서 정확도를 올리기
+위해 Ad-hoc한 patch 등이 코드에 상당량 포함된 상태인데 이를 정제하고 체계화하는
+노력이 필요합니다.
+
+== Contributing to gimchi
+ 
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
+* Fork the project
+* Start a feature/bugfix branch
+* Commit and push until you are happy with your contribution
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+== Copyright
+
+Copyright (c) 2011 Junegunn Choi. See LICENSE.txt for
+further details.
+

data/README.rdoc

@@ -0,0 +1,118 @@
+# encoding: UTF-8
+
+= gimchi
+
+Gimchi is a simple Ruby gem which knows how to handle Korean strings. It knows
+how to dissect Korean characters into its 3 components, namely chosung,
+jungsung and optional jongsung. It knows how Korean sentences are pronounced
+and how they're written in roman alphabet. 
+
+Gimchi (only partially) implements the following rules dictated by
+The National Institute of The Korean Language (http://www.korean.go.kr)
+* Korean Standard Pronunciation
+* Korean romanization
+
+== Usage
+
+=== Creating Gimchi::Korean instance
+  ko = Gimchi::Korean.new
+
+=== Checks if the given character is in Korean alphabet
+  ko.korean_char? 'ㄱ'           # true
+  ko.complete_korean_char? 'ㄱ'  # false
+
+  ko.korean_char? 'ㅏ'           # true
+  ko.complete_korean_char? 'ㅏ'  # false
+
+  ko.korean_char? '가'           # true
+  ko.complete_korean_char? '가'  # true
+
+=== Usage of Gimchi::Korean::Char
+  arr = ko.dissect '이것은 한글입니다.'
+    # [이, 것, 은, " ", 한, 글, 입, 니, 다, "."]
+
+  arr[4].class                   # Gimchi::Korean::Char
+
+  arr[4].chosung                 # "ㅎ"
+  arr[4].jungsung                # "ㅏ"
+  arr[4].jongsung                # "ㄴ"
+  arr[4].to_a                    # ["ㅎ", "ㅏ", "ㄴ"]
+  arr[4].to_s                    # "한"
+
+  arr[4].chosung = 'ㄷ'
+  arr[4].jongsung = 'ㄹ'
+  arr[4].to_s                    # "달"
+  arr[4].complete?               # true
+  arr[4].partial?                # false
+
+  arr[4].chosung = nil
+  arr[4].jongsung = nil
+  arr[4].complete?               # false
+  arr[4].partial?                # true
+
+=== Reading numbers in Korean
+  ko.read_number(1999)         # "천 구백 구십 구"
+  ko.read_number(- 100.123)    # "마이너스 백점일이삼"
+  ko.read_number("153,101,202,333.321")
+  ko.read_number("153,191,100,678.3214")
+    	# "천 오백 삼십 일억 구천 백 십만 육백 칠십 팔점삼이일사"
+
+  # Age, Time ( -살, -시 )
+  ko.read_number("20살")       # "스무살"
+  ko.read_number("13 살")      # "열세 살"
+  ko.read_number("7시 30분")   # "일곱시 삼십분"
+
+=== Standard pronunciation (partially implemented)
+  str = "됐어 됐어 이제 그런 가르침은 됐어 매일 아침 7 시 30 분까지 우릴 조그만 교실로 몰아넣고"
+  ko.pronounce str
+    # "돼써 돼써 이제 그런 가르치믄 돼써 매일 아침 일곱 시 삼십 분까지 우릴 조그만 교실로 모라너코"
+
+  ko.pronounce str, :slur => true
+    # "돼써 돼써 이제 그런 가르치믄 돼써 매이 라치 밀곱 씨 삼십 뿐까지 우릴 조그만 교실로 모라너코"
+
+  ko.pronounce str, :pronounce_each_char => true
+    # "됃어 됃어 이제 그런 가르침은 됃어 매일 아침 일곱 시 삼십 분까지 우릴 조그만 교실로 몰아너고"
+
+  ko.pronounce str, :number => false
+    # "돼써 돼써 이제 그런 가르치믄 돼써 매일 아침 7 시 30 분까지 우릴 조그만 교실로 모라너코"
+
+=== Romanization (partially implemented)
+  str = "됐어 됐어 이제 그런 가르침은 됐어 매일 아침 7 시 30 분까지 우릴 조그만 교실로 몰아넣고"
+
+  ko.romanize str
+    # "Dwaesseo dwaesseo ije geureon gareuchimeun dwaesseo mae-il achim ilgop si samsip bunkkaji uril jogeuman gyosillo moraneoko"
+  ko.romanize str, :slur => true
+    # "Dwaesseo dwaesseo ije geureon gareuchimeun dwaesseo mae-i rachi milgop ssi samsip ppunkkaji uril jogeuman gyosillo moraneoko"
+  ko.romanize str, :as_pronounced => false
+    # "Dwaet-eo dwaet-eo ije geureon gareuchim-eun dwaet-eo mae-il achim ilgop si samsip bunkkaji uril jogeuman gyosillo mol-aneogo"
+  ko.romanize str, :number => false
+    # "Dwaesseo dwaesseo ije geureon gareuchimeun dwaesseo mae-il achim 7 si 30 bunkkaji uril jogeuman gyosillo moraneoko"
+
+== Limitation of the implementation
+
+Unfortunately in order to implement the complete specification of Korean
+pronunciation and romanization, we need NLP, hugh Korean dictionaries and even
+semantic analysis of the given string. And even with all those complex
+processing, we cannot guarantee 100% accuracy of the output. So yes, that is
+definitely not what this gem tries to achieve. Gimchi tries to achieve "some"
+level of accuracy with relatively simple code.
+
+Currently, Gimchi code containts a lot of ad-hoc (possibly invalid) patches
+that try to improve the quality of the output, which should better be
+refactored anytime soon.
+
+== Contributing to gimchi
+ 
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
+* Fork the project
+* Start a feature/bugfix branch
+* Commit and push until you are happy with your contribution
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+== Copyright
+
+Copyright (c) 2011 Junegunn Choi. See LICENSE.txt for
+further details.
+

data/config/default.yml

@@ -0,0 +1,156 @@
+---
+structure:
+    chosung:  [ㄱ, ㄲ, ㄴ, ㄷ, ㄸ, ㄹ, ㅁ, ㅂ, ㅃ, ㅅ, ㅆ, ㅇ, ㅈ, ㅉ, ㅊ, ㅋ, ㅌ, ㅍ, ㅎ]
+    jungsung: [ㅏ, ㅐ, ㅑ, ㅒ, ㅓ, ㅔ, ㅕ, ㅖ, ㅗ, ㅘ, ㅙ, ㅚ, ㅛ, ㅜ, ㅝ, ㅞ, ㅟ, ㅠ, ㅡ, ㅢ, ㅣ]
+    jongsung: [ㄱ, ㄲ, ㄳ, ㄴ, ㄵ, ㄶ, ㄷ, ㄹ, ㄺ, ㄻ, ㄼ, ㄽ, ㄾ, ㄿ, ㅀ, ㅁ, ㅂ, ㅄ, ㅅ, 
+                ㅆ, ㅇ, ㅈ, ㅊ, ㅋ, ㅌ, ㅍ, ㅎ]
+
+    fortis map:
+        ㄱ: ㄲ
+        ㄷ: ㄸ
+        ㅂ: ㅃ
+        ㅅ: ㅆ
+        ㅈ: ㅉ
+
+    double consonant map:
+        ㄳ: [ㄱ, ㅅ]
+        ㄵ: [ㄴ, ㅈ]
+        ㄶ: [ㄴ, ㅎ]
+        ㄺ: [ㄹ, ㄱ]
+        ㄻ: [ㄹ, ㅁ]
+        ㄼ: [ㄹ, ㅂ]
+        ㄽ: [ㄹ, ㅅ]
+        ㄾ: [ㄹ, ㅌ]
+        ㄿ: [ㄹ, ㅍ]
+        ㅀ: [ㄹ, ㅎ]
+        ㅄ: [ㅂ, ㅅ]
+
+pronouncer:
+    jongsung sound:
+        ㄱ: ㄱ
+        ㄲ: ㄱ
+        ㄳ: ㄱ
+        ㄴ: ㄴ
+        ㄵ: ㄴ
+        ㄶ: ㄴ
+        ㄷ: ㄷ
+        ㄹ: ㄹ
+        ㄺ: ㄱ
+        ㄻ: ㅁ
+        ㄼ: ㄹ
+        ㄽ: ㄹ
+        ㄾ: ㅌ
+        ㄿ: ㅂ
+        ㅀ: ㄹ
+        ㅁ: ㅁ
+        ㅂ: ㅂ
+        ㅄ: ㅂ
+        ㅅ: ㄷ
+        ㅆ: ㄷ
+        ㅇ: ㅇ
+        ㅈ: ㄷ
+        ㅊ: ㄷ
+        ㅋ: ㄱ
+        ㅌ: ㄷ
+        ㅍ: ㅂ
+        ㅎ:
+    transformation:
+        # changing the order affects the quality of the transformation
+        sequence:
+            - rule_16
+            - rule_17
+            - rule_18
+            - rule_19
+            - rule_5_1
+            - rule_5_3
+            - rule_30
+            - rule_23
+            - rule_24
+            - rule_25
+            - rule_12
+            - rule_20
+            - rule_10
+            - rule_27
+            - rule_9
+            - rule_11
+            - rule_14
+            - rule_13
+            - rule_15
+        blocking rule:
+            rule_16: [rule_30]
+
+number:
+    negative: 마이너스
+    decimal point: 점
+    units: ["", 만, 억, 조, 경, 해, 자, 양, 구, 간, 정, 재, 극, 항하사, 아승기, 나유타, 불가사의, 무량대수]
+    digits: [영, 일, 이, 삼, 사, 오, 육, 칠, 팔, 구]
+
+    # 정수형일 때 또다른 표현법 (나이, 시간)
+    alt notation:
+        when suffix:
+            살:
+                max: 
+            시:
+                max: 12
+        tenfolds: [열, 스물, 서른, 마흔, 쉰, 예순, 일흔, 여든, 아흔, 백]
+        digits: ["", 한, 두, 세, 네, 다섯, 여섯, 일곱, 여덟, 아홉]
+        post substitution:
+            물살: 무살
+            물시: 무살
+
+romanization:
+    chosung:
+        ㄱ: g
+        ㄲ: kk
+        ㅋ: k
+        ㄷ: d
+        ㄸ: tt
+        ㅌ: t
+        ㅂ: b
+        ㅃ: pp
+        ㅍ: p
+        ㅈ: j
+        ㅉ: jj
+        ㅊ: ch
+        ㅅ: s
+        ㅆ: ss
+        ㅎ: h
+        ㄴ: n
+        ㅁ: m
+        ㄹ: r
+        ㅇ: "-"
+    jungsung:
+        ㅏ: a
+        ㅓ: eo
+        ㅗ: o
+        ㅜ: u
+        ㅡ: eu
+        ㅣ: i
+        ㅐ: ae
+        ㅔ: e
+        ㅚ: oe
+        ㅟ: wi
+        ㅑ: ya
+        ㅕ: yeo
+        ㅛ: yo
+        ㅠ: yu
+        ㅒ: yae
+        ㅖ: ye
+        ㅘ: wa
+        ㅙ: wae
+        ㅝ: wo
+        ㅞ: we
+        ㅢ: ui
+    jongsung:
+        ㄱ: k
+        ㄴ: n
+        ㄷ: t
+        ㄹ: l
+        ㅁ: m
+        ㅂ: p
+        ㅇ: ng
+    post substitution:
+        # 제2항 [붙임 2]‘ㄹ’은 모음 앞에서는 ‘ｒ’로, 자음 앞이나 어말에서는
+        # ‘ｌ’로 적는다. 단, ‘ㄹㄹ’은 ‘ll’로 적는다.
+        lr: ll
+

data/lib/gimchi.rb

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+# encoding: UTF-8
+# Junegunn Choi (junegunn.c@gmail.com)
+
+require 'gimchi/korean'
+require 'gimchi/char'
+require 'gimchi/pronouncer'
+

data/lib/gimchi/char.rb

@@ -0,0 +1,104 @@
+# encoding: UTF-8
+
+module Gimchi
+class Korean
+	# Class representing each Korean character.
+	# chosung, jungsung and jongsung can be get and set.
+	#
+	# to_s merges components into a String.
+	# to_a returns the three components.
+	class Char
+		attr_reader :org
+		attr_reader :chosung, :jungsung, :jongsung
+
+		def initialize kor, kchar
+			raise ArgumentError('Not a korean character') unless kor.korean_char? kchar
+
+			@kor = kor
+			@cur = []
+			if @kor.complete_korean_char? kchar
+				c = kchar.unpack('U').first
+				n = c - 0xAC00
+				# '가' ~ '깋' -> 'ㄱ'
+				n1 = n / (21 * 28)
+				# '가' ~ '깋'에서의 순서
+				n = n % (21 * 28)
+				n2 = n / 28;
+				n3 = n % 28;
+				self.chosung = @kor.chosungs[n1]
+				self.jungsung = @kor.jungsungs[n2]
+				self.jongsung = ([nil] + @kor.jongsungs)[n3]
+			elsif (@kor.chosungs + @kor.jongsungs).include? kchar
+				self.chosung = kchar
+			elsif @kor.jungsungs.include? kchar
+				self.jungsung = kchar
+			end
+
+			@org = self.dup
+		end
+
+		# recombine components into korean character
+		def to_s
+			if chosung.nil? && jungsung.nil?
+				""
+			elsif chosung && jungsung
+				n1, n2, n3 = 
+				n1 = @kor.chosungs.index(chosung) || 0
+				n2 = @kor.jungsungs.index(jungsung) || 0
+				n3 = ([nil] + @kor.jongsungs).index(jongsung) || 0
+				[ 0xAC00 + n1 * (21 * 28) + n2 * 28 + n3 ].pack('U')
+			else
+				chosung || jungsung
+			end
+		end
+
+		def chosung= c
+			raise ArgumentError.new('Invalid chosung component') if
+					c && @kor.chosungs.include?(c) == false
+			@chosung = c && c.dup.extend(Component).tap { |e| e.kor = @kor }
+		end
+
+		def jungsung= c
+			raise ArgumentError.new('Invalid jungsung component') if
+					c && @kor.jungsungs.include?(c) == false
+			@jungsung = c && c.dup.extend(Component).tap { |e| e.kor = @kor }
+		end
+
+		def jongsung= c
+			raise ArgumentError.new('Invalid jongsung component') if
+					c && @kor.jongsungs.include?(c) == false
+			@jongsung = c && c.dup.extend(Component).tap { |e| e.kor = @kor }
+		end
+
+		# to_a returns the three components.
+		def to_a
+			[chosung, jungsung, jongsung]
+		end
+
+		# Check if this is a complete Korean character
+		def complete?
+			chosung.nil? == false && jungsung.nil? == false
+		end
+
+		# Check if this is a non-complete Korean character
+		# e.g. ㅇ, ㅏ
+		def partial?
+			chosung.nil? || jungsung.nil?
+		end
+
+	private
+		# nodoc #
+		module Component
+			attr_accessor :kor
+
+			def vowel?
+				kor.jungsungs.include? self
+			end
+
+			def consonant?
+				self != 'ㅇ' && kor.chosungs.include?(self)
+			end
+		end#Component
+	end#Char
+end#Korean
+end#Gimchi